DeepAI AI Chat
Log In Sign Up

The Deep Minimizing Movement Scheme

by   Hyung Ju Hwang, et al.
KAIST 수리과학과

Solutions of certain partial differential equations (PDEs) are often represented by the steepest descent curves of corresponding functionals. Minimizing movement scheme was developed in order to study such curves in metric spaces. Especially, Jordan-Kinderlehrer-Otto studied the Fokker-Planck equation in this way with respect to the Wasserstein metric space. In this paper, we propose a deep learning-based minimizing movement scheme for approximating the solutions of PDEs. The proposed method is highly scalable for high-dimensional problems as it is free of mesh generation. We demonstrate through various kinds of numerical examples that the proposed method accurately approximates the solutions of PDEs by finding the steepest descent direction of a functional even in high dimensions.


page 14

page 15

page 20


Data driven gradient flows

We present a framework enabling variational data assimilation for gradie...

Deep least-squares methods: an unsupervised learning-based numerical method for solving elliptic PDEs

This paper studies an unsupervised deep learning-based numerical approac...

Deep Finite Volume Method for High-Dimensional Partial Differential Equations

In this paper, we propose a new deep learning method, named finite volum...

Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks

Gradient flows are a powerful tool for optimizing functionals in general...

Normalized Wolfe-Powell-type Local Minimax Method for Finding Multiple Unstable Solutions of Nonlinear Elliptic PDEs

The local minimax method (LMM) proposed in [Y. Li and J. Zhou, SIAM J. S...

Geometric Hermite Interpolation in ℝ^n by Refinements

We describe a general approach for constructing a broad class of operato...